bunkerweb

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill explicitly acknowledges that external data like logs and request headers are attacker-controlled. It includes a dedicated 'Data, not instructions' section that mandates the agent ignore any instructions or commands found within processed data.
  • [COMMAND_EXECUTION]: Orchestrates the deployment of WAF infrastructure using docker, kubectl, and systemctl commands. These actions are standard for the skill's primary purpose of installing and managing a security proxy.
  • [EXTERNAL_DOWNLOADS]: Fetches installation scripts and configuration data from official vendor sources, specifically GitHub and the BunkerWeb package registry. The instructions emphasize verifying checksums and avoid piping downloads directly to the shell.
  • [PRIVILEGE_ESCALATION]: Utilizes sudo for Linux package installation and service management. This level of privilege is necessary and expected for installing a system-wide Web Application Firewall.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 09:09 AM